© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 111215
    Prev
    Next
    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stark
    -0.08
     costes
    -0.08
     coste
    -0.08
    reate
    -0.07
    Factories
    -0.07
     highlighting
    -0.07
     brittle
    -0.07
     docking
    -0.07
     pillars
    -0.07
     zal
    -0.07
    POSITIVE LOGITS
    iov
    0.09
     제한
    0.09
     Tempor
    0.08
    atura
    0.08
     ozi
    0.08
     ajout
    0.08
     bof
    0.08
     Taken
    0.08
     hơi
    0.07
    Restriction
    0.07
    Activations Density 0.013%

    No Known Activations